Can it run?
Runs well
Using Q4_K_M in llama.cpp
Fit status
Runs well
Decode
118.4 tok/s
TTFT
1636 ms
Safe context
8K
Memory
8.0 GB / 10.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 118.4 tok/s | 2379 ms | 8K |
| Chat | B | Runs well | 118.4 tok/s | 892 ms | 8K |
| Coding | B | Runs well | 118.4 tok/s | 1636 ms | 8K |
| RAG | C | Tight fit | 118.4 tok/s | 2974 ms | 8K |
| Reasoning | B | Runs well | 118.4 tok/s | 1933 ms | 8K |
How Aya Expanse 8B (8B params) fits at each quantization level on RTX 3080 10GB (10.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | D36 |
Q3_K_S | 3 | 3.9 GB | Low | D38 |
NVFP4 | 4 | 4.5 GB | Medium | D39 |
Q4_K_M | 4 | 4.9 GB | Medium | D40 |
Q5_K_M | 5 | 5.8 GB | High | C42 |
Q6_KBest for your GPU | 6 | 6.6 GB | High | C43 |
Q8_0 | 8 | 8.6 GB | Very High | C44 |
F16 | 16 | 16.4 GB | Maximum | F0 |
huggingface-cli download aya-expanse-8b